{"list":"other","total":107,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1809.02165","title":"Deep Learning for Generic Object Detection: A Survey","created":"2018-09-06","cited_by_count":392},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1808.00278","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","created":"2018-08-01","cited_by_count":235},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"1903.06530","title":"Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection","created":"2019-03-12","cited_by_count":177},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151},{"id":"2106.07597","title":"MLPerf Tiny Benchmark","created":"2021-06-14","cited_by_count":124},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98},{"id":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89},{"id":"1903.10979","title":"DetNAS: Backbone Search for Object Detection","created":"2019-03-26","cited_by_count":81},{"id":"2008.06120","title":"Can weight sharing outperform random architecture search? An investigation with TuNAS","created":"2020-08-13","cited_by_count":68},{"id":"2004.14525","title":"MobileDets: Searching for Object Detection Architectures for Mobile Accelerators","created":"2020-04-30","cited_by_count":55},{"id":"1906.04423","title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","created":"2019-06-11","cited_by_count":53},{"id":"1906.09607","title":"Densely Connected Search Space for More Flexible Neural Architecture Search","created":"2019-06-23","cited_by_count":52},{"id":"2306.11369","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","created":"2023-06-20","cited_by_count":52},{"id":"2010.12023","title":"Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection","created":"2020-10-22","cited_by_count":50},{"id":"1908.03299","title":"ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection","created":"2019-08-09","cited_by_count":44},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38},{"id":"1812.00124","title":"NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection","created":"2018-12-01","cited_by_count":37},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36},{"id":"1907.10586","title":"Distilled Siamese Networks for Visual Tracking","created":"2019-07-24","cited_by_count":34},{"id":"2003.03961","title":"BiDet: An Efficient Binarized Object Detector","created":"2020-03-09","cited_by_count":33},{"id":"2003.11818","title":"Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection","created":"2020-03-26","cited_by_count":32},{"id":"1711.06929","title":"Deep Gaussian Mixture Models","created":"2017-11-18","cited_by_count":30},{"id":"1808.04285","title":"Unsupervised Hard Example Mining from Videos for Improved Object Detection","created":"2018-08-13","cited_by_count":30},{"id":"2009.05697","title":"YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design","created":"2020-09-12","cited_by_count":24},{"id":"2212.03332","title":"Edge Impulse: An MLOps Platform for Tiny Machine Learning","created":"2022-11-02","cited_by_count":24},{"id":"2205.14942","title":"Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles","created":"2022-05-30","cited_by_count":22},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21},{"id":"2109.11496","title":"LGD: Label-guided Self-distillation for Object Detection","created":"2021-09-23","cited_by_count":19},{"id":"1912.01106","title":"MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices","created":"2019-12-02","cited_by_count":18},{"id":"2006.12986","title":"FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search","created":"2020-06-21","cited_by_count":17},{"id":"2405.15199","title":"ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models","created":"2024-05-24","cited_by_count":17},{"id":"1909.02293","title":"Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection","created":"2019-09-05","cited_by_count":16},{"id":"2110.00337","title":"PhiNets: a scalable backbone for low-power AI at the edge","created":"2021-10-01","cited_by_count":16},{"id":"2307.07813","title":"TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation","created":"2023-07-15","cited_by_count":16},{"id":"1807.11013","title":"Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages","created":"2018-07-29","cited_by_count":15},{"id":"2306.12010","title":"Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection","created":"2023-06-21","cited_by_count":15},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15},{"id":"1909.13396","title":"REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs","created":"2019-09-29","cited_by_count":13},{"id":"1906.01878","title":"pCAMP: Performance Comparison of Machine Learning Packages on the Edges","created":"2019-06-05","cited_by_count":12},{"id":"2201.01863","title":"CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs","created":"2022-01-05","cited_by_count":11},{"id":"2307.05999","title":"Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems","created":"2023-07-12","cited_by_count":11},{"id":"1909.09934","title":"Structured Binary Neural Networks for Image Recognition","created":"2019-09-22","cited_by_count":10},{"id":"2109.04459","title":"SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learning","created":"2021-09-09","cited_by_count":10},{"id":"2307.07662","title":"MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression","created":"2023-07-14","cited_by_count":10},{"id":"2012.13587","title":"Inception Convolution with Efficient Dilation Search","created":"2020-12-25","cited_by_count":9},{"id":"2310.16898","title":"MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory","created":"2023-10-25","cited_by_count":9},{"id":"2111.06503","title":"AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator","created":"2021-11-10","cited_by_count":7},{"id":"2203.10747","title":"EAutoDet: Efficient Architecture Search for Object Detection","created":"2022-03-21","cited_by_count":7},{"id":"1804.06332","title":"Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving","created":"2018-04-17","cited_by_count":6},{"id":"2311.05494","title":"Object-centric Cross-modal Feature Distillation for Event-based Object Detection","created":"2023-11-09","cited_by_count":6},{"id":"2409.16808","title":"A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices","created":"2024-09-25","cited_by_count":6},{"id":"2009.04247","title":"Binarized Neural Architecture Search for Efficient Object Recognition","created":"2020-09-08","cited_by_count":5},{"id":"2404.12403","title":"Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity","created":"2024-04-15","cited_by_count":5},{"id":"2504.09685","title":"Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?","created":"2025-04-13","cited_by_count":5},{"id":"2204.10546","title":"Depth Pruning with Auxiliary Networks for TinyML","created":"2022-04-22","cited_by_count":4}],"next_cursor":"100"}